NetAmerica Alliance Blog
Welcome to the NetAmerica Alliance Blog, where you can explore wireless industry news, trends, and commentary from us and around the industry.
Scientists Use Mobile, Twitter Data to Accurately Estimate Crowd Sizes
Ever wonder about, or been skeptical of, estimates of crowd sizes? Scientists working at Warwick Business School's (WBS) Data Science Lab in central England have found that use of mobile phones and Twitter might provide estimates of crowd sizes that are surprisingly accurate.
Gathering and analyzing mobile phone and Twitter data from fans at a soccer match and Linate Airport in Milan, three WBS Data Science Lab scientists were able to produce accurate estimates of crowd sizes at any given point in time, according to a May 27 Warwick Business School news release. A brief report of their research was published May 28 by the Royal Society for Open Science.
The method and techniques used by the Data Science Lab scientists could be of value in emergency situations, such as evacuations and crowd disasters, WBS points out.
"Measuring crowd size is a difficult task, as the hugely varying estimates we see of the number of people at protests underline. Given that most people now carry a mobile phone with them, we wondered if we could measure the number of people in a given location simply by analyzing data on usage of these mobile phones," one of the researchers, Federick Botta, explained.
"We found that this automatically generated data provides an excellent basis for estimating the size of a crowd. Quick and accurate measurements of crowd size could be of vital use for police and other authorities charged with avoiding crowd disasters."
The WBS scientists analyzed two months worth of mobile phone and Twitter data provided by Telecom Italia in conducting their research. That included text messages and the number of Internet connections, as well as incoming and outgoing voice calls. Based on the data, they were able to place users in a particular location, as well as count their number.
WBS Data Science Lab Associate Professor Dr. Tobias Preis elaborated on the research: "We plotted mobile phone calls, Twitter and SMS activity in the geographical area in which the San Siro [Milan's football/soccer stadium] is located and in all three we observed 10 distinct spikes. We found that the dates these spikes occurred coincided exactly with the dates on which the 10 football matches took place in the stadium.
"Furthermore, we noted that the relative sizes of the spikes strongly resembled the official attendance figure for each match. By drawing on historic Internet activity in the San Siro, we were able to generate estimates of the number of attendees which fell within 13 per cent of the true value."
The researchers were able to calibrate their model using official estimates of attendance provided by officials at the San Siro stadium. They found that the relationship between Internet usage and match attendance was the strongest, "perhaps because smartphones automatically check services such as email, without the need for the user to actively intervene," Associate Professor of Behavioral Science Dr. Suzy Moat added.